mlsanityData to 7 Oct 2026

The Replicator Dynamic, Chain Components and the Response Graph

arXiv 2209.15230 ↗First posted 30 Sep 2022cs.GT cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

In this paper we examine the relationship between the flow of the replicator dynamic, the continuum limit of Multiplicative Weights Update, and a game's response graph. We settle an open problem establishing that under the replicator, sink chain components -- a topological notion of long-run outcome of a dynamical system -- always exist and are approximated by the sink connected components of the game's response graph. More specifically, each sink chain component contains a sink connected component of the response graph, as well as all mixed strategy profiles whose support consists of pure profiles in the same connected component, a set we call the content of the connected component. As a corollary, all profiles are chain recurrent in games with strongly connected response graphs. In any two-player game sharing a response graph with a zero-sum game, the sink chain component is unique. In two-player zero-sum and potential games the sink chain components and sink connected components are in a one-to-one correspondence, and we conjecture that this holds in all games.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 10 of its 44 references that are in the map. First posted on arXiv 30 Sep 2022.

Builds on

10 of 44 references.

References · 10

  1. 2017Cycles in adversarial regularized learningcited by 122
  2. 2018The Mechanics of n-Player Differentiable Gamescited by 118
  3. 2020Game-Theoretic Multiagent Reinforcement Learningcited by 92
  4. 2019α-Rank: Multi-Agent Evaluation by Evolutioncited by 50
  5. 2020No-regret learning and mixed Nash equilibria: They do not mixcited by 49
  6. 2019Vortices Instead of Equilibria in MinMax Optimization: Chaos and Butterfly Effects of Online Learning in Zero-Sum Gamescited by 24
  7. 2020Chaos, Extremism and Optimism: Volume Analysis of Learning in Gamescited by 16
  8. 2021Learning in Matrix Games can be Arbitrarily Complexcited by 11
  9. 2022Nash, Conley, and Computation: Impossibility and Incompleteness in Game Dynamicscited by 4
  10. 2022The graph structure of two-player gamescited by 3

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1; 2025: 1.

3 papers.